Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3069 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7907. Min Act: -0.1700

Data Index: 8299979 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.8106. Min Act: -0.1700

Data Index: 2002983 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.8014. Min Act: -0.1700

Data Index: 344531 (Open Web Text)

Max Activating Token Index: 546

Text #3

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7648. Min Act: -0.1700

Data Index: 7253696 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7682. Min Act: -0.1700

Data Index: 3781118 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7752. Min Act: -0.1700

Data Index: 8745095 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7917. Min Act: -0.1700

Data Index: 7037231 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7426. Min Act: -0.1700

Data Index: 4991894 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7223. Min Act: -0.1700

Data Index: 5878947 (Open Web Text)

Max Activating Token Index: 802

Text #9

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7413. Min Act: -0.1700

Data Index: 5856342 (Open Web Text)

Max Activating Token Index: 867

Text #10

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.6734. Min Act: -0.1700

Data Index: 3276838 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7345. Min Act: -0.1700

Data Index: 2919773 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7073. Min Act: -0.1700

Data Index: 4512314 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.6860. Min Act: -0.1700

Data Index: 321493 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7020. Min Act: -0.1700

Data Index: 7965495 (Open Web Text)

Max Activating Token Index: 974

Text #15

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.6890. Min Act: -0.1700

Data Index: 1087104 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.6931. Min Act: -0.1700

Data Index: 7217589 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7064. Min Act: -0.1700

Data Index: 4926340 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7069. Min Act: -0.1700

Data Index: 2994684 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 2.8106. Min Range: -2.8106

Max Act: 2.7060. Min Act: -0.1700

Data Index: 1457018 (Open Web Text)

Max Activating Token Index: 645